roikoren755 38c498b8e3 [Performance] Cublas Bf16 Gate with Fp32 Output (#35121) ...

Signed-off-by: Roi Koren <roik@nvidia.com>

2026-02-26 16:51:28 -08:00

..

kernels

[CPU][Feat] Enable KleidiAI INT8_W4A8 for all input dtypes (#34890)

2026-02-26 05:00:10 +00:00

layers

[Performance] Cublas Bf16 Gate with Fp32 Output (#35121)

2026-02-26 16:51:28 -08:00

model_loader

add mixed precision support for modelopt (#35047)

2026-02-26 21:56:24 +00:00

models

[Performance] Cublas Bf16 Gate with Fp32 Output (#35121)

2026-02-26 16:51:28 -08:00

offloader

[offloader] v2: Hide weight onloading latency via prefetching (#29941)

2026-02-25 17:20:59 -08:00

warmup

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

[Model Bash][DSR1] Add selective dynamic shape marking for CustomOp (#34900)

2026-02-21 19:28:01 -05:00

parameter.py

[QeRL] Layerwise Reloading (#32133)

2026-01-30 08:50:05 -07:00

utils.py

[BugFix] Fix EPLB fail for MoeFP4 model with Marlin backend (#33262)

2026-01-29 16:52:11 +08:00